{"id":"https://openalex.org/W2128353077","doi":"https://doi.org/10.1101/gr.8.11.1154","title":"How to Interpret an Anonymous Bacterial Genome: Machine Learning Approach to Gene Identification","display_name":"How to Interpret an Anonymous Bacterial Genome: Machine Learning Approach to Gene Identification","publication_year":1998,"publication_date":"1998-11-01","ids":{"openalex":"https://openalex.org/W2128353077","doi":"https://doi.org/10.1101/gr.8.11.1154","mag":"2128353077","pmid":"https://pubmed.ncbi.nlm.nih.gov/9847079"},"language":"en","primary_location":{"id":"doi:10.1101/gr.8.11.1154","doi":"https://doi.org/10.1101/gr.8.11.1154","is_oa":true,"landing_page_url":"https://doi.org/10.1101/gr.8.11.1154","pdf_url":"http://genome.cshlp.org/content/8/11/1154.full.pdf","source":{"id":"https://openalex.org/S43092948","display_name":"Genome Research","issn_l":"1088-9051","issn":["1088-9051","1549-5469"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315909","host_organization_name":"Cold Spring Harbor Laboratory Press","host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome Research","raw_type":"journal-article"},"volume":null,"type":"preprint","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"http://genome.cshlp.org/content/8/11/1154.full.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111969026","display_name":"William S. Hayes","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William S. Hayes","raw_affiliation_strings":["School of Biology, Georgia Institute of Technology, Atlanta, Georgia 30332-0230, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biology, Georgia Institute of Technology, Atlanta, Georgia 30332-0230, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057317686","display_name":"Mark Yu. Borodovsky","orcid":"https://orcid.org/0000-0002-1401-4046","observed_orcids":["https://orcid.org/0000-0002-1401-4046"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Borodovsky","raw_affiliation_strings":["School of Biology, Georgia Institute of Technology, Atlanta, Georgia 30332-0230 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biology, Georgia Institute of Technology, Atlanta, Georgia 30332-0230 USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":117,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"11","first_page":"1154","last_page":"1171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gene-discovery","display_name":"gene discovery","score":0.6119999885559082},{"id":"https://openalex.org/keywords/bacterial-genome-annotation","display_name":"bacterial genome annotation","score":0.7559999823570251},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.8450000286102295},{"id":"https://openalex.org/keywords/protein-coding-regions","display_name":"protein-coding regions","score":0.8159999847412109},{"id":"https://openalex.org/keywords/noncoding-regions","display_name":"non-coding regions","score":0.984000027179718},{"id":"https://openalex.org/keywords/codon-usage","display_name":"codon usage","score":0.8109999895095825},{"id":"https://openalex.org/keywords/horizontal-gene-transfer","display_name":"horizontal gene transfer","score":0.9150000214576721},{"id":"https://openalex.org/keywords/methanocaldococcus-jannaschii","display_name":"Methanococcus jannaschii","score":0.9179999828338623},{"id":"https://openalex.org/keywords/helicobacter-pylori","display_name":"Helicobacter pylori","score":0.9679999947547913}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7857158780097961},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.777578592300415},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.6548576354980469},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.6530733108520508},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6454678773880005},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.6135725975036621},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.5906975865364075},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5179859399795532},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.4990553855895996},{"id":"https://openalex.org/C91779695","wikidata":"https://www.wikidata.org/wiki/Q3780824","display_name":"Coding region","level":3,"score":0.4645886719226837},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.452825129032135},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.17044422030448914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15625444054603577},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D008432","descriptor_name":"Mathematical Computing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1101/gr.8.11.1154","doi":"https://doi.org/10.1101/gr.8.11.1154","is_oa":true,"landing_page_url":"https://doi.org/10.1101/gr.8.11.1154","pdf_url":"http://genome.cshlp.org/content/8/11/1154.full.pdf","source":{"id":"https://openalex.org/S43092948","display_name":"Genome Research","issn_l":"1088-9051","issn":["1088-9051","1549-5469"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315909","host_organization_name":"Cold Spring Harbor Laboratory Press","host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome Research","raw_type":"journal-article"},{"id":"pmid:9847079","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/9847079","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome research","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1101/gr.8.11.1154","doi":"https://doi.org/10.1101/gr.8.11.1154","is_oa":true,"landing_page_url":"https://doi.org/10.1101/gr.8.11.1154","pdf_url":"http://genome.cshlp.org/content/8/11/1154.full.pdf","source":{"id":"https://openalex.org/S43092948","display_name":"Genome Research","issn_l":"1088-9051","issn":["1088-9051","1549-5469"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315909","host_organization_name":"Cold Spring Harbor Laboratory Press","host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome Research","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2128353077.pdf","grobid_xml":"https://content.openalex.org/works/W2128353077.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1606770439","https://openalex.org/W1608218663","https://openalex.org/W1652691445","https://openalex.org/W1921645034","https://openalex.org/W1947962930","https://openalex.org/W1971403296","https://openalex.org/W1981053737","https://openalex.org/W2011063408","https://openalex.org/W2017205882","https://openalex.org/W2025666214","https://openalex.org/W2030205072","https://openalex.org/W2032870665","https://openalex.org/W2039680623","https://openalex.org/W2041652393","https://openalex.org/W2045403483","https://openalex.org/W2047521874","https://openalex.org/W2052503008","https://openalex.org/W2067680474","https://openalex.org/W2099111195","https://openalex.org/W2100882223","https://openalex.org/W2110132014","https://openalex.org/W2113824405","https://openalex.org/W2125873768","https://openalex.org/W2134153749","https://openalex.org/W2147694156","https://openalex.org/W2152180708","https://openalex.org/W2152222870","https://openalex.org/W2158714788","https://openalex.org/W2160053034","https://openalex.org/W2164249947","https://openalex.org/W2166187656","https://openalex.org/W4239833500","https://openalex.org/W4295127969"],"related_works":["https://openalex.org/W7097482137","https://openalex.org/W1128165272","https://openalex.org/W2143235667","https://openalex.org/W2152180708","https://openalex.org/W2160053034","https://openalex.org/W2282348497","https://openalex.org/W2088607230","https://openalex.org/W2106090237","https://openalex.org/W1834463255","https://openalex.org/W2604046539"],"abstract_inverted_index":{"In":[0,140],"this":[1],"report":[2,206],"we":[3],"address":[4],"the":[5,45,57,62,83,119,125,137,141,144,160,172,179,197,207,213,225,230],"problem":[6],"of":[7,11,36,44,52,64,67,95,105,115,121,127,191,199,209,212,216,248],"accurate":[8],"statistical":[9,50],"modeling":[10],"DNA":[12],"sequences,":[13],"either":[14],"coding":[15],"or":[16],"noncoding,":[17],"for":[18,41,99,195],"a":[19,25,96,100],"bacterial":[20,74,222],"species":[21],"whose":[22],"genome":[23,46],"(or":[24],"large":[26],"portion)":[27],"was":[28,238],"sequenced":[29,221],"but":[30],"not":[31],"yet":[32],"characterized":[33],"experimentally.":[34],"Availability":[35],"these":[37],"models":[38,66,78,104,117,234],"is":[39,91],"critical":[40],"successful":[42],"solution":[43],"annotation":[47],"task":[48],"by":[49,111,171,178,236,251],"methods":[51],"gene":[53,152],"finding.":[54],"We":[55,157,205],"present":[56],"method,":[58],"GeneMark-Genesis,":[59],"which":[60],"learns":[61],"parameters":[63],"Markov":[65],"protein-coding":[68,106,116],"and":[69,85,136,143,154,202,232],"noncoding":[70,97],"regions":[71],"from":[72,134],"anonymous":[73],"genomic":[75],"sequence.":[76],"These":[77],"are":[79,108,149],"subsequently":[80],"used":[81,194],"in":[82,132],"GeneMark":[84],"GeneMark.hmm":[86,226],"gene-finding":[87],"programs.":[88],"Although":[89],"there":[90,148],"basically":[92],"one":[93,135,164],"model":[94,162,181],"region":[98,107],"given":[101],"genome,":[102],"several":[103],"automatically":[109],"obtained":[110],"GeneMark-Genesis.":[112],"The":[113,188],"diversity":[114,120,126],"reflects":[118],"oligonucleotide":[122],"compositions,":[123],"particularly":[124],"codon":[128],"usage":[129],"strategies":[130],"observed":[131],"genes":[133,167,176,245],"same":[138],"genome.":[139],"simplest":[142],"most":[145],"important":[146],"case,":[147],"just":[150],"two":[151],"models-typical":[153],"atypical":[155,161,180,233,244],"ones.":[156],"show":[158],"that":[159,168,228],"allows":[163],"to":[165,183,240],"predict":[166,241],"escape":[169],"identification":[170],"typical":[173,231],"model.":[174],"Many":[175],"predicted":[177],"appear":[182],"be":[184],"horizontally":[185],"transferred":[186],"genes.":[187],"early":[189],"versions":[190],"GeneMark-Genesis":[192,217,237],"were":[193],"annotating":[196],"genomes":[198],"Methanoccocus":[200],"jannaschii":[201],"Helicobacter":[203],"pylori.":[204],"results":[208],"accuracy":[210],"testing":[211],"full-scale":[214],"version":[215],"on":[218],"10":[219],"completely":[220],"genomes.":[223],"Interestingly,":[224],"program":[227],"employed":[229],"defined":[235],"able":[239],"683":[242],"new":[243],"with":[246],"176":[247],"them":[249],"confirmed":[250],"similarity":[252],"search.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}
